{"total":90,"rows":[{"id":"2504.01990","title":"Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems","created":"2025-03-31","cited_by_count":126,"area":"agents"},{"id":"2502.10391","title":"MM-RLHF: The Next Step Forward in Multimodal LLM Alignment","created":"2025-02-14","cited_by_count":83,"area":"mllm"},{"id":"2412.10400","title":"Reinforcement Learning Enhanced LLMs: A Survey","created":"2024-12-05","cited_by_count":71,"area":"lr"},{"id":"2504.12328","title":"A Comprehensive Survey of Reward Models: Taxonomy, Applications, Challenges, and Future","created":"2025-04-12","cited_by_count":53,"area":"alignment"},{"id":"2408.06266","title":"Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment","created":"2024-08-12","cited_by_count":46,"area":"alignment"},{"id":"2410.10148","title":"AlphaDPO: Adaptive Reward Margin for Direct Preference Optimization","created":"2024-10-14","cited_by_count":29,"area":"alignment"},{"id":"2510.08529","title":"CoMAS: Co-Evolving Multi-Agent Systems via Interaction Rewards","created":"2025-10-09","cited_by_count":29,"area":"agents"},{"id":"2410.15595","title":"A Comprehensive Survey of Direct Preference Optimization: Datasets, Theories, Variants, and Applications","created":"2024-10-21","cited_by_count":27,"area":"lr"},{"id":"2412.00383","title":"Unified Parameter-Efficient Unlearning for LLMs","created":"2024-11-30","cited_by_count":25,"area":"lr"},{"id":"2411.11072","title":"Multilingual Large Language Models: A Systematic Survey","created":"2024-11-17","cited_by_count":18,"area":null},{"id":"2502.01930","title":"Robust LLM Alignment via Distributionally Robust Direct Preference Optimization","created":"2025-02-04","cited_by_count":18,"area":"alignment"},{"id":"2505.02666","title":"A Survey on Progress in LLM Alignment from the Perspective of Reward Design","created":"2025-05-05","cited_by_count":15,"area":"alignment"},{"id":"2503.17928","title":"Debiasing Multimodal Large Language Models via Noise-Aware Preference Optimization","created":"2025-03-23","cited_by_count":14,"area":"mllm"},{"id":"2501.18578","title":"R.I.P.: Better Models by Survival of the Fittest Prompts","created":"2025-01-30","cited_by_count":13,"area":null},{"id":"2506.03690","title":"Robust Preference Optimization via Dynamic Target Margins","created":"2025-06-04","cited_by_count":13,"area":"alignment"},{"id":"2502.18635","title":"Faster, Cheaper, Better: Multi-Objective Hyperparameter Optimization for LLM and RAG Systems","created":"2025-02-25","cited_by_count":12,"area":"rag"},{"id":"2508.18312","title":"What Matters in Data for DPO?","created":"2025-08-23","cited_by_count":12,"area":"alignment"},{"id":"2509.16736","title":"Towards Transparent and Incentive-Compatible Collaboration in Decentralized LLM Multi-Agent Systems: A Blockchain-Driven Approach","created":"2025-09-20","cited_by_count":12,"area":"agents"},{"id":"2509.22611","title":"Quantile Advantage Estimation: Stabilizing RLVR for LLM Reasoning","created":"2025-09-26","cited_by_count":11,"area":"lr"},{"id":"2503.02783","title":"Teaching Your Models to Understand Code via Focal Preference Alignment","created":"2025-03-04","cited_by_count":10,"area":"alignment"},{"id":"2410.05102","title":"SparsePO: Controlling Preference Alignment of LLMs via Sparse Token Masks","created":"2024-10-07","cited_by_count":9,"area":"alignment"},{"id":"2504.03612","title":"AIR: A Systematic Analysis of Annotations, Instructions, and Response Pairs in Preference Dataset","created":"2025-04-04","cited_by_count":9,"area":"alignment"},{"id":"2504.15477","title":"In-context Ranking Preference Optimization","created":"2025-04-21","cited_by_count":9,"area":"alignment"},{"id":"2505.19601","title":"Preference Optimization by Estimating the Ratio of the Data Distribution","created":"2025-05-26","cited_by_count":9,"area":"alignment"},{"id":"2502.02095","title":"LongDPO: Unlock Better Long-form Generation Abilities for LLMs via Critique-augmented Stepwise Information","created":"2025-02-04","cited_by_count":8,"area":null},{"id":"2502.13173","title":"Thinking Preference Optimization","created":"2025-02-17","cited_by_count":8,"area":"lr"},{"id":"2411.17265","title":"Systematic Reward Gap Optimization for Mitigating VLM Hallucinations","created":"2024-11-26","cited_by_count":7,"area":"mllm"},{"id":"2504.09802","title":"Enhancing Reasoning Abilities of Small LLMs with Cognitive Alignment","created":"2025-04-14","cited_by_count":7,"area":"lr"},{"id":"2508.20181","title":"Mitigating Hallucinations in Multimodal LLMs via Object-aware Preference Optimization","created":"2025-08-27","cited_by_count":7,"area":"mllm"},{"id":"2502.20847","title":"Gradient Imbalance in Direct Preference Optimization","created":"2025-02-28","cited_by_count":6,"area":"alignment"},{"id":"2506.06366","title":"AI Agent Behavioral Science","created":"2025-06-04","cited_by_count":6,"area":"agents"},{"id":"2605.01123","title":"PERSA: Reinforcement Learning for Professor-Style Personalized Feedback with LLMs","created":"2026-05-01","cited_by_count":6,"area":"alignment"},{"id":"2410.08316","title":"COS-DPO: Conditioned One-Shot Multi-Objective Fine-Tuning Framework","created":"2024-10-10","cited_by_count":5,"area":"alignment"},{"id":"2502.01667","title":"Refining Alignment Framework for Diffusion Models with Intermediate-Step Preference Ranking","created":"2025-02-01","cited_by_count":5,"area":"diffusion"},{"id":"2502.13177","title":"KL Penalty Control via Perturbation for Direct Preference Optimization","created":"2025-02-18","cited_by_count":5,"area":"alignment"},{"id":"2505.23316","title":"Proximalized Preference Optimization for Diverse Feedback Types: A Decomposed Perspective on DPO","created":"2025-05-29","cited_by_count":5,"area":"alignment"},{"id":"2409.17169","title":"REAL: Response Embedding-based Alignment for LLMs","created":"2024-09-17","cited_by_count":4,"area":"alignment"},{"id":"2503.07426","title":"RePO: Understanding Preference Learning Through ReLU-Based Optimization","created":"2025-03-10","cited_by_count":4,"area":"alignment"},{"id":"2504.16628","title":"ParetoHqD: Fast Offline Multiobjective Alignment of Large Language Models using Pareto High-quality Data","created":"2025-04-23","cited_by_count":4,"area":"alignment"},{"id":"2505.17859","title":"Scalable Valuation of Human Feedback through Provably Robust Model Alignment","created":"2025-05-23","cited_by_count":4,"area":"alignment"},{"id":"2511.15767","title":"TB or Not TB: Coverage-Driven Direct Preference Optimization for Verilog Stimulus Generation","created":"2025-11-19","cited_by_count":4,"area":"alignment"},{"id":"2512.00706","title":"Optimizing LVLMs with On-Policy Data for Effective Hallucination Mitigation","created":"2025-11-30","cited_by_count":4,"area":"mllm"},{"id":"2411.14871","title":"Preference Alignment for Diffusion Model via Explicit Denoised Distribution Estimation","created":"2024-11-22","cited_by_count":3,"area":"diffusion"},{"id":"2505.21907","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","created":"2025-05-28","cited_by_count":3,"area":"alignment"},{"id":"2507.19586","title":"Mitigating Geospatial Knowledge Hallucination in Large Language Models: Benchmarking and Dynamic Factuality Aligning","created":"2025-07-25","cited_by_count":3,"area":null},{"id":"2509.26063","title":"Fading to Grow: Growing Preference Ratios via Preference Fading Discrete Diffusion for Recommendation","created":"2025-09-30","cited_by_count":3,"area":"diffusion"},{"id":"2510.17245","title":"On Efficiency-Effectiveness Trade-off of Diffusion-based Recommenders","created":"2025-10-20","cited_by_count":3,"area":"diffusion"},{"id":"2510.19384","title":"Learning Noise-Resilient and Transferable Graph-Text Alignment via Dynamic Quality Assessment","created":"2025-10-22","cited_by_count":3,"area":null},{"id":"2601.00623","title":"DA-DPO: Cost-efficient Difficulty-aware Preference Optimization for Reducing MLLM Hallucinations","created":"2026-01-02","cited_by_count":3,"area":"mllm"},{"id":"2506.04272","title":"Understanding the Impact of Sampling Quality in Direct Preference Optimization","created":"2025-06-03","cited_by_count":2,"area":"alignment"},{"id":"2509.23564","title":"Clean First, Align Later: Benchmarking Preference Data Cleaning for Reliable LLM Alignment","created":"2025-09-28","cited_by_count":2,"area":"alignment"},{"id":"2603.18113","title":"VC-Soup: Value-Consistency Guided Multi-Value Alignment for Large Language Models","created":"2026-03-18","cited_by_count":2,"area":"alignment"},{"id":"2605.04539","title":"RLearner-LLM: Balancing Logical Grounding and Fluency in Large Language Models via Hybrid Direct Preference Optimization","created":"2026-05-06","cited_by_count":2,"area":"alignment"},{"id":"2502.13019","title":"Oreo: A Plug-in Context Reconstructor to Enhance Retrieval-Augmented Generation","created":"2025-02-18","cited_by_count":1,"area":"rag"},{"id":"2506.02015","title":"OSPO: Object-Centric Self-Improving Preference Optimization for Text-to-Image Generation","created":"2025-05-28","cited_by_count":1,"area":"mllm"},{"id":"2506.05260","title":"LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs","created":"2025-06-05","cited_by_count":1,"area":"alignment"},{"id":"2507.20181","title":"SGPO: Self-Generated Preference Optimization based on Self-Improver","created":"2025-07-27","cited_by_count":1,"area":"alignment"},{"id":"2509.22851","title":"Adaptive Margin RLHF via Preference over Preferences","created":"2025-09-26","cited_by_count":1,"area":"alignment"},{"id":"2510.05342","title":"Margin Adaptive DPO: Leveraging Reward Model for Granular Control in Preference Optimization","created":"2025-10-06","cited_by_count":1,"area":"alignment"},{"id":"2510.14459","title":"Holdout-Loss-Based Data Selection for LLM Finetuning via In-Context Learning","created":"2025-10-16","cited_by_count":1,"area":"alignment"},{"id":"2510.15061","title":"Antislop: A Comprehensive Framework for Identifying and Eliminating Repetitive Patterns in Language Models","created":"2025-10-16","cited_by_count":1,"area":null},{"id":"2512.10237","title":"Multi-dimensional Preference Alignment by Conditioning Reward Itself","created":"2025-12-11","cited_by_count":1,"area":"diffusion"},{"id":"2601.06180","title":"MixDPO: Modeling Preference Strength for Pluralistic Alignment","created":"2026-01-07","cited_by_count":1,"area":"alignment"},{"id":"2602.09533","title":"Autoregressive Direct Preference Optimization","created":"2026-02-10","cited_by_count":1,"area":"alignment"},{"id":"2603.22165","title":"ACPO: Counteracting Likelihood Displacement in Vision-Language Alignment with Asymmetric Constraints","created":"2026-03-23","cited_by_count":1,"area":"mllm"},{"id":"2604.14951","title":"RaTA-Tool: Retrieval-based Tool Selection with Multimodal Large Language Models","created":"2026-04-16","cited_by_count":1,"area":"mllm"},{"id":"2505.21893","title":"SIPO: Stabilized and Improved Preference Optimization for Aligning Diffusion Models","created":"2025-05-28","cited_by_count":0,"area":"diffusion"},{"id":"2508.09653","title":"On Negative-aware Preference Optimization for Recommendation","created":"2025-08-13","cited_by_count":0,"area":"alignment"},{"id":"2509.24207","title":"Humanline: Online Alignment as Perceptual Loss","created":"2025-09-29","cited_by_count":0,"area":"lr"},{"id":"2510.09887","title":"Overconfident and Blind to Details: Fixing Prompt Insensitivity with Abductive Preference Learning","created":"2025-10-10","cited_by_count":0,"area":"alignment"},{"id":"2601.04212","title":"TrueBrief: Faithful Summarization through Small Language Models","created":"2025-12-12","cited_by_count":0,"area":null},{"id":"2601.22385","title":"SP^2DPO: An LLM-assisted Semantic Per-Pair DPO Generalization","created":"2026-01-29","cited_by_count":0,"area":"alignment"},{"id":"2601.23222","title":"Region-Normalized DPO for Medical Image Segmentation under Noisy Judges","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2603.04968","title":"When Weak LLMs Speak with Confidence, Preference Alignment Gets Stronger","created":"2026-03-05","cited_by_count":0,"area":"alignment"},{"id":"2603.04974","title":"VRM: Teaching Reward Models to Understand Authentic Human Preferences","created":"2026-03-05","cited_by_count":0,"area":"alignment"},{"id":"2604.24804","title":"Intrinsic Mutual Information as a Modulator for Preference Optimization","created":"2026-04-27","cited_by_count":0,"area":"alignment"},{"id":"2605.00327","title":"DynamicPO: Dynamic Preference Optimization for Recommendation","created":"2026-05-01","cited_by_count":0,"area":"alignment"},{"id":"2605.06049","title":"Fusion in Your Way: Aligning Image Fusion with Heterogeneous Demands via Direct Preference Optimization","created":"2026-05-07","cited_by_count":0,"area":"diffusion"},{"id":"2605.10863","title":"DGPO: Beyond Pairwise Preferences with Directional Consistent Groupwise Optimization","created":"2026-05-11","cited_by_count":0,"area":"alignment"},{"id":"2605.10981","title":"$\\xi$-DPO: Direct Preference Optimization via Ratio Reward Margin","created":"2026-05-09","cited_by_count":0,"area":"alignment"},{"id":"2605.12288","title":"TokenRatio: Principled Token-Level Preference Optimization via Ratio Matching","created":"2026-05-12","cited_by_count":0,"area":"alignment"},{"id":"2605.28010","title":"Confidence-Orchestrated Self-Evolution against Uncertain LLM Feedback","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2607.10147","title":"REVA-PO: Stabilizing Reinforcement Learning for Chest X-ray Report Generation","created":"2026-07-11","cited_by_count":0,"area":"deeprl"},{"id":"2607.27366","title":"BridgeAlign: Bridging Preference Alignment for Humanities and Social Sciences","created":"2026-07-29","cited_by_count":0,"area":"alignment"},{"id":"2608.09568","title":"Se-DPO: Self-Evolving Token Credit for Direct Preference Optimization","created":"2026-08-10","cited_by_count":0,"area":"alignment"},{"id":"2608.27032","title":"Disentangling Optimization Scale from Preference Scale in DPO","created":"2026-08-27","cited_by_count":0,"area":"alignment"},{"id":"2609.05899","title":"AlignDiff: Exploiting Model-Intrinsic Information for Better Preference Data Selection","created":"2026-09-05","cited_by_count":0,"area":"alignment"},{"id":"2609.16532","title":"Style-Debiased DPO: Updating LLM Knowledge with Factuality-Aware Synthetic Preference Data","created":"2026-09-15","cited_by_count":0,"area":"alignment"},{"id":"2609.38647","title":"Uncertainty-Normalized Margins for Direct Preference Optimization","created":"2026-09-29","cited_by_count":0,"area":"alignment"},{"id":"2610.19095","title":"Similar Models, Broken Odds: Where Luce's Axiom Fails in Chatbot Arena","created":"2026-10-13","cited_by_count":0,"area":"alignment"}],"next_cursor":null}